edipretoro/scrarls
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Updating the extraction of fields

Browse Source
This commit is contained in:
edipretoro 2026-01-01 21:22:10 +01:00
parent ada99be262
commit 15e1f837c8
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
scrarls.py
View File

@ -54,13 +54,13 @@ class TvShow(CrawlSpider):
def parse(self, response):
for article in response.css("article"):
item = TvShowItem()
item['article_id'] = article.attrib['id'],
item['article_title'] = article.css('h1.entry-title > a::text').get(),
item['title'] = article.css('.entry-summary > p:nth-child(4) > strong::text').get(),
item['date'] = self.parse_date(article.css('.entry-meta-header-before::text').getall()[1].strip()),
item['summary'] = article.xpath('.//div[@class="entry-summary"]/node()').extract(),
item['image_url'] = article.css('.entry-summary > p > img::attr(src)').get(),
item['download_url'] = article.css('.entry-summary > p > a[href ^= "https://rapidgator"]::attr(href)').get()
item['post_id'] = article.attrib['id']
item['post_title'] = article.css('h1.entry-title > a::text').get()
item['title'] = article.css('.entry-summary > p:nth-child(4) > strong::text').get()
item['date'] = self.parse_date(article.css('.entry-meta-header-before::text').getall()[1].strip())
item['summary'] = "".join(article.xpath('.//div[@class="entry-summary"]/node()').extract())
item['image_url'] = article.css('.entry-summary > p > img::attr(src)').get()
item['download_url'] = "#".join(article.css('.entry-summary > p > a[href ^= "https://rapidgator"]::attr(href)').extract())
yield item
def parse_date(self, formatted_date: str):